GS-SDF: LiDAR-Augmented Gaussian Splatting and Neural SDF for Geometrically Consistent Rendering and Reconstruction

Jianheng Liu, Yunfei Wan, Bowen Wang, Chunran Zheng, Jiarong Lin and Fu Zhang,
The University of Hong Kong,
Paper Video Code

Abstract

A MultiModal Mapping (M2Mapping) Framework for LiDAR-Visual Systems

This paper presents a unified surface reconstruction and rendering framework for LiDAR-visual systems, integrating Neural Radiance Fields (NeRF) and Neural Distance Fields (NDF) to recover both appearance and structural information from posed images and point clouds. We address the structural visible gap between NeRF and NDF by utilizing a visible-aware occupancy map to classify space into the free, occupied, visible unknown, and background regions. This classification facilitates the recovery of a complete appearance and structure of the scene. We unify the training of the NDF and NeRF using a spatial-varying scale SDF-to-density transformation for levels of detail for both structure and appearance. The proposed method leverages the learned NDF for structure-aware NeRF training by an adaptive sphere tracing sampling strategy for accurate structure rendering. In return, NeRF further refines structural in recovering missing or fuzzy structures in the NDF. Extensive experiments demonstrate the superior quality and versatility of the proposed method across various scenarios.

Shape Regularization

Illustration of different geometric regularization. The blue splats represent the initial splat, and the orange splats represent the optimized splat. The dashed lines represent the optimization directions.

Video

Experiments

Replica

We emphasize the issues of extrapolation rendering consistency by uniformly sampling positions and orientations in each scene to generate the extrapolation dataset from Replica.

InstantNGP
H2Mapping
3DGS
MonoGS
2DGS
PGSR
Ours
M2Mapping

FAST-LIVO2

InstantNGP
3DGS
2DGS
PGSR
RR
RR+CR
M2Mapping
Ours(RR+SR)

* RR: Render Regularization, CR: Center Regularization, SR: Structure Regularization.

Surface Reconstruction Results

Compressed Mesh.

FAST-LIVO2

Campus

Sculpture

Culture

Drive

Station

CBD

SYSU

BibTeX


          @misc{liu2025gssdflidaraugmentedgaussiansplatting,
            title={GS-SDF: LiDAR-Augmented Gaussian Splatting and Neural SDF for Geometrically Consistent Rendering and Reconstruction}, 
            author={Jianheng Liu and Yunfei Wan and Bowen Wang and Chunran Zheng and Jiarong Lin and Fu Zhang},
            year={2025},
            eprint={2503.10170},
            archivePrefix={arXiv},
            primaryClass={cs.RO},
            url={https://arxiv.org/abs/2503.10170}, 
          }